Uploaded September 2026 | Updated November 2026, 2 hours ago
Netflix built an async inference platform: a unified framework for batch inference and near-real-time serving on a single stack.
At Ray Summit 2026, Wenbing Bai and Naveen Somasundaram from Netflix cover patterns for multimodal inference with Ray and vLLM, including batching, GPU utilization, and common abstractions, plus practical lessons from running these workloads in production.
You'll leave with patterns for unifying batch and near-real-time inference on one stack.
Liked this video? Check out other Ray Summit breakout session recordings: youtube.com/playlist?list=PLZNaJyYZRPdo
Subscribe to our YouTube channel to stay up-to-date on the future of AI: youtube.com/c/anyscale
đź”— Connect with us:
LinkedIn: linkedin.com/company/joinanyscale
X: https://x.com/anyscalecompute
Website: anyscale.com
Netflix built an async inference platform: a unified framework for batch inference and near-real-time serving on a single stack.
At Ray Summit 2026, Wenbing Bai and Naveen Somasundaram from Netflix cover patterns for multimodal inference with Ray and vLLM, including batching, GPU utilization, and common abstractions, plus practical lessons from running these workloads in production.
You'll leave with patterns for unifying batch and near-real-time inference on one stack.
Liked this video? Check out other Ray Summit breakout session recordings: youtube.com/playlist?list=PLZNaJyYZRPdo
Subscribe to our YouTube channel to stay up-to-date on the future of AI: youtube.com/c/anyscale
đź”— Connect with us:
LinkedIn: linkedin.com/company/joinanyscale
X: https://x.com/anyscalecompute
Website: anyscale.com










